© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    5. Pythia-70M-Deduped
    7. MLP Post
    9. 0-MLP-SM
    11. 26210
    Prev
    Next
    INDEX
    Explanations

    mentions of Poland and associated geographical references

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    ctigges/pythia-70m-deduped__mlp-sm_processed/0-mlp-sm
    Prompts (Dashboard)
    32,768 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    32,768
    Data Type
    torch.float32
    Hook Name
    blocks.0.hook_mlp_out
    Hook Layer
    0
    Architecture
    standard
    Context Size
    128
    Dataset
    EleutherAI/the_pile_deduplicated
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    71
    +0.15
    0.9%
    369
    +0.13
    0.7%
    246
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    71
    +0.15
    0.01
    511
    +0.13
    0.01
    54
    +0.11
    0.01
    Negative Logits
    ĥ½
    -2.85
    ľ
    -2.54
    ¶
    -2.54
    Ĩ
    -2.52
    Ķ
    -2.48
    ¾
    -2.42
    į
    -2.36
    Ŀ
    -2.29
    ĵ
    -2.27
    ĺ
    -2.27
    POSITIVE LOGITS
    borg
    1.71
    lei
    1.67
    bolt
    1.65
    leen
    1.61
    une
    1.60
    shire
    1.58
    istine
    1.58
     recognizes
    1.56
    illac
    1.56
    emaker
    1.55
    Activations Density 0.081%

    No Known Activations